© 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. 18491
    Prev
    Next
    INDEX
    Explanations

    DOCTYPE

    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
    or
    -0.08
    father
    -0.08
    Likelihood
    -0.08
    Necessary
    -0.08
    the
    -0.08
    ologically
    -0.07
    numer
    -0.07
    baby
    -0.07
    initis
    -0.07
    The
    -0.07
    POSITIVE LOGITS
     html
    0.13
    >↵
    0.11
    	html
    0.10
    ><
    0.10
     Mouse
    0.10
    doctype
    0.09
    html
    0.09
     THEY
    0.09
     Html
    0.09
     İnsan
    0.09
    Activations Density 0.000%

    No Known Activations