© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18956
    Prev
    Next
    INDEX
    Explanations

    32

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =df
    -0.08
     use
    -0.08
    =models
    -0.08
    	ft
    -0.08
     डेटा
    -0.07
    डेट
    -0.07
     cpf
    -0.07
    =forms
    -0.07
    ్స్
    -0.07
    =\'
    -0.07
    POSITIVE LOGITS
    alent
    0.09
    ക്കാര
    0.09
    .Stored
    0.08
    processable
    0.08
    _possible
    0.08
    angible
    0.08
    _uploaded
    0.08
    szyst
    0.08
    _COMP
    0.08
    _comp
    0.07
    Activations Density 0.001%

    No Known Activations