© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19157
    Prev
    Next
    INDEX
    Explanations

    needed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estaremos
    -0.10
     serían
    -0.10
     dersom
    -0.10
     würden
    -0.09
     estarão
    -0.09
     એવી
    -0.09
     저는
    -0.09
     estarán
    -0.09
     estaría
    -0.09
     যদি
    -0.09
    POSITIVE LOGITS
     needed
    0.28
     necessary
    0.24
     అవస
    0.23
     necessário
    0.22
     आवश्यक
    0.21
    needed
    0.21
     required
    0.21
     જરૂરી
    0.21
     nepiecieš
    0.21
    _needed
    0.21
    Activations Density 0.010%

    No Known Activations