Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 117482
    Prev
    Next
    INDEX
    Explanations

    Code and Movie scripts

    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
    Attempts
    -0.08
     জল
    -0.08
    PA
    -0.07
     drains
    -0.07
    Drain
    -0.07
    败
    -0.07
    Passed
    -0.07
    ွ
    -0.07
     ruwa
    -0.07
    AK
    -0.07
    POSITIVE LOGITS
     melanoma
    0.09
     resort
    0.08
     Anita
    0.08
    암
    0.08
    .permission
    0.08
     operatie
    0.08
     perfume
    0.08
     Anime
    0.08
     noir
    0.08
     sympat
    0.08
    Activations Density 0.000%

    No Known Activations