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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75689
    Prev
    Next
    INDEX
    Explanations

    alibis/murder mysteries

    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
    igere
    -0.08
     caution
    -0.08
     Signs
    -0.08
    (TM
    -0.08
    Signs
    -0.07
     fades
    -0.07
     Ursachen
    -0.07
     dims
    -0.07
    hui
    -0.07
     näh
    -0.07
    POSITIVE LOGITS
     التاريخ
    0.08
    Protected
    0.08
     sheltered
    0.07
     strtotime
    0.07
     comprov
    0.07
     reportedly
    0.07
    iles
    0.07
    نوان
    0.07
     claimed
    0.07
    Ment
    0.07
    Activations Density 0.001%

    No Known Activations