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. 112785
    Prev
    Next
    INDEX
    Explanations

    has

    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
    _Name
    -0.08
    ಸಿ
    -0.08
     prince
    -0.08
     Liz
    -0.08
    _Checked
    -0.08
    _Enable
    -0.08
    _Button
    -0.08
     treated
    -0.08
    zka
    -0.08
    හා
    -0.08
    POSITIVE LOGITS
    opping
    0.08
    orting
    0.08
     koje
    0.08
    ర్థ
    0.07
     ניס
    0.07
    flt
    0.07
     portanto
    0.07
    duit
    0.07
    failed
    0.07
     elems
    0.07
    Activations Density 0.001%

    No Known Activations