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. 103204
    Prev
    Next
    INDEX
    Explanations

    cam

    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
     credentials
    -0.09
    .ship
    -0.08
     tactics
    -0.08
    .email
    -0.08
     refugees
    -0.08
     overwhelm
    -0.07
     primit
    -0.07
     پیام
    -0.07
     internationally
    -0.07
     مشابه
    -0.07
    POSITIVE LOGITS
    _clk
    0.09
     Conte
    0.08
    thane
    0.08
    _CLK
    0.08
     canopy
    0.08
     clocks
    0.08
     Compensation
    0.08
    чын
    0.08
     Cay
    0.08
     Dorm
    0.08
    Activations Density 0.004%

    No Known Activations