© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64289
    Prev
    Next
    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     construit
    -0.08
     সংগ
    -0.08
    هم
    -0.08
     gebouwen
    -0.08
     бух
    -0.07
     består
    -0.07
    ох
    -0.07
     organis
    -0.07
    basis
    -0.07
     المسلحة
    -0.07
    POSITIVE LOGITS
     �
    0.08
    ivt
    0.08
    iett
    0.08
    0.07
    Pol
    0.07
    TV
    0.07
    147
    0.07
    念
    0.07
     reduct
    0.07
     Yaz
    0.07
    Activations Density 0.000%
    No Known Activations