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. 26795
    Prev
    Next
    INDEX
    Explanations

    v

    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
    <|endoftext|>
    -0.09
    _COORD
    -0.07
     گست
    -0.07
    .springframework
    -0.07
     rever
    -0.07
     широк
    -0.07
    _'.$
    -0.07
     arbitr
    -0.07
    Muk
    -0.07
    .expand
    -0.07
    POSITIVE LOGITS
     byen
    0.09
     cilvē
    0.08
     freezing
    0.08
     yelled
    0.08
     embryos
    0.08
     mesin
    0.08
    gera
    0.08
     rog
    0.07
     Imm
    0.07
     quelli
    0.07
    Activations Density 0.009%

    No Known Activations