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. 58377
    Prev
    Next
    INDEX
    Explanations

    hex

    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
    .Login
    -0.09
    _enc
    -0.08
    503
    -0.08
    500
    -0.08
    Enc
    -0.08
    _eff
    -0.07
    /login
    -0.07
    _squared
    -0.07
     flask
    -0.07
    genre
    -0.07
    POSITIVE LOGITS
     mẹ
    0.10
     والأس
    0.08
     hexadecimal
    0.08
     cotid
    0.08
    	byte
    0.08
    .UInt
    0.08
     ATR
    0.08
    	ct
    0.08
     Pearl
    0.07
     kollha
    0.07
    Activations Density 0.004%

    No Known Activations