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. 103258
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    -0.08
    ்வ
    -0.08
    ర్జ
    -0.08
     haqq
    -0.07
     dhaq
    -0.07
    ooda
    -0.07
     dha
    -0.07
     sjed
    -0.07
     nade
    -0.07
     Islamist
    -0.07
    POSITIVE LOGITS
     Comité
    0.08
    �
    0.08
    WEBPACK
    0.08
     jeweils
    0.08
    公里
    0.08
     respectivamente
    0.07
     espos
    0.07
     हजार
    0.07
    @qq
    0.07
    ølge
    0.07
    Activations Density 0.003%

    No Known Activations