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. 15-RESID-POST-AA
    6. 18797
    Prev
    Next
    INDEX
    Explanations

    Calculating time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _PATH
    -0.09
    -0.08
     देकर
    -0.08
    近年来
    -0.07
     ನೀಡಿ
    -0.07
     ప్రస్తుతం
    -0.07
     derzeit
    -0.07
    PATH
    -0.07
    ,今年
    -0.07
    _VEC
    -0.07
    POSITIVE LOGITS
     cri
    0.08
     kreat
    0.08
    rowning
    0.08
     identities
    0.08
     identiteit
    0.08
     datetime
    0.08
     midnight
    0.07
    ジュ
    0.07
    	Return
    0.07
     timeval
    0.07
    Activations Density 0.002%

    No Known Activations